From: Jaegeuk Hanse <jaegeuk.hanse@gmail.com>
To: Maxim Patlasov <mpatlasov@parallels.com>
Cc: miklos@szeredi.hu, dev@parallels.com, xemul@parallels.com,
fuse-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org,
jbottomley@parallels.com, linux-mm@kvack.org,
viro@zeniv.linux.org.uk, linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH 14/14] mm: Account for WRITEBACK_TEMP in balance_dirty_pages
Date: Thu, 22 Nov 2012 21:27:30 +0800 [thread overview]
Message-ID: <50AE2842.3060509@gmail.com> (raw)
In-Reply-To: <20121121115314.20471.52148.stgit@maximpc.sw.ru>
On 11/21/2012 08:01 PM, Maxim Patlasov wrote:
> Added linux-mm@ to cc:. The patch can stand on it's own.
>
>> Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
>> counter is high enough. This prevents us from having too many dirty
>> pages on fuse, thus giving the userspace part of it a chance to write
>> stuff properly.
>>
>> Note, that the existing balance logic is per-bdi, i.e. if the fuse
>> user task gets stuck in the function this means, that it either
>> writes to the mountpoint it serves (but it can deadlock even without
>> the writeback) or it is writing to some _other_ dirty bdi and in the
>> latter case someone else will free the memory for it.
> Signed-off-by: Maxim V. Patlasov <MPatlasov@parallels.com>
> Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
> ---
> mm/page-writeback.c | 3 ++-
> 1 files changed, 2 insertions(+), 1 deletions(-)
>
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 830893b..499a606 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -1220,7 +1220,8 @@ static void balance_dirty_pages(struct address_space *mapping,
> */
> nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
> global_page_state(NR_UNSTABLE_NFS);
> - nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
> + nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK) +
> + global_page_state(NR_WRITEBACK_TEMP);
>
Could you explain NR_WRITEBACK_TEMP is used for accounting what? And
when it will increase?
> global_dirty_limits(&background_thresh, &dirty_thresh);
>
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Jaegeuk Hanse <jaegeuk.hanse@gmail.com>
To: Maxim Patlasov <mpatlasov@parallels.com>
Cc: miklos@szeredi.hu, dev@parallels.com, xemul@parallels.com,
fuse-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org,
jbottomley@parallels.com, linux-mm@kvack.org,
viro@zeniv.linux.org.uk, linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH 14/14] mm: Account for WRITEBACK_TEMP in balance_dirty_pages
Date: Thu, 22 Nov 2012 21:27:30 +0800 [thread overview]
Message-ID: <50AE2842.3060509@gmail.com> (raw)
In-Reply-To: <20121121115314.20471.52148.stgit@maximpc.sw.ru>
On 11/21/2012 08:01 PM, Maxim Patlasov wrote:
> Added linux-mm@ to cc:. The patch can stand on it's own.
>
>> Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
>> counter is high enough. This prevents us from having too many dirty
>> pages on fuse, thus giving the userspace part of it a chance to write
>> stuff properly.
>>
>> Note, that the existing balance logic is per-bdi, i.e. if the fuse
>> user task gets stuck in the function this means, that it either
>> writes to the mountpoint it serves (but it can deadlock even without
>> the writeback) or it is writing to some _other_ dirty bdi and in the
>> latter case someone else will free the memory for it.
> Signed-off-by: Maxim V. Patlasov <MPatlasov@parallels.com>
> Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
> ---
> mm/page-writeback.c | 3 ++-
> 1 files changed, 2 insertions(+), 1 deletions(-)
>
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 830893b..499a606 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -1220,7 +1220,8 @@ static void balance_dirty_pages(struct address_space *mapping,
> */
> nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
> global_page_state(NR_UNSTABLE_NFS);
> - nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
> + nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK) +
> + global_page_state(NR_WRITEBACK_TEMP);
>
Could you explain NR_WRITEBACK_TEMP is used for accounting what? And
when it will increase?
> global_dirty_limits(&background_thresh, &dirty_thresh);
>
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-11-22 13:27 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-16 17:04 [PATCH v2 00/14] fuse: An attempt to implement a write-back cache policy Maxim Patlasov
2012-11-16 17:04 ` Maxim Patlasov
[not found] ` <20121116170123.3196.93431.stgit-vWG5eQQidJHciZdyczg/7Q@public.gmane.org>
2012-11-16 17:05 ` [PATCH 01/14] fuse: Linking file to inode helper Maxim Patlasov
2012-11-16 17:05 ` Maxim Patlasov
2012-11-16 17:05 ` [PATCH 02/14] fuse: Getting file for writeback helper Maxim Patlasov
2012-11-16 17:05 ` Maxim Patlasov
2012-11-16 17:06 ` [PATCH 03/14] fuse: Prepare to handle short reads Maxim Patlasov
2012-11-16 17:06 ` Maxim Patlasov
2012-11-16 17:07 ` [PATCH 04/14] fuse: Prepare to handle multiple pages in writeback Maxim Patlasov
2012-11-16 17:07 ` Maxim Patlasov
2012-11-16 17:07 ` [PATCH 05/14] fuse: Connection bit for enabling writeback Maxim Patlasov
2012-11-16 17:07 ` Maxim Patlasov
2012-11-16 17:07 ` [PATCH 06/14] fuse: Trust kernel i_size only Maxim Patlasov
2012-11-16 17:07 ` Maxim Patlasov
[not found] ` <20121116170731.3196.47157.stgit-vWG5eQQidJHciZdyczg/7Q@public.gmane.org>
2012-12-05 16:39 ` [PATCH] fuse: Trust kernel i_size only - v2 Maxim Patlasov
2012-12-05 16:39 ` Maxim Patlasov
2012-12-05 16:40 ` [PATCH] fuse: Implement writepages and write_begin/write_end callbacks " Maxim Patlasov
2012-12-05 16:40 ` Maxim Patlasov
2012-11-16 17:09 ` [PATCH 07/14] fuse: Update i_mtime on buffered writes Maxim Patlasov
2012-11-16 17:09 ` Maxim Patlasov
2012-11-16 17:09 ` [PATCH 08/14] fuse: Flush files on wb close Maxim Patlasov
2012-11-16 17:09 ` Maxim Patlasov
2012-11-16 17:09 ` [PATCH 09/14] fuse: Implement writepages and write_begin/write_end callbacks Maxim Patlasov
2012-11-16 17:09 ` Maxim Patlasov
2012-11-16 17:09 ` [PATCH 10/14] fuse: fuse_writepage_locked() should wait on writeback Maxim Patlasov
2012-11-16 17:09 ` Maxim Patlasov
2012-11-16 17:10 ` [PATCH 11/14] fuse: fuse_flush() " Maxim Patlasov
2012-11-16 17:10 ` Maxim Patlasov
2012-11-16 17:10 ` [PATCH 12/14] fuse: Fix O_DIRECT operations vs cached writeback misorder Maxim Patlasov
2012-11-16 17:10 ` Maxim Patlasov
[not found] ` <20121116171012.3196.35933.stgit-vWG5eQQidJHciZdyczg/7Q@public.gmane.org>
2012-12-05 16:43 ` [PATCH] fuse: Fix O_DIRECT operations vs cached writeback misorder - v2 Maxim Patlasov
2012-12-05 16:43 ` Maxim Patlasov
2012-11-16 17:10 ` [PATCH 13/14] fuse: Turn writeback cache on Maxim Patlasov
2012-11-16 17:10 ` Maxim Patlasov
2012-11-16 17:10 ` [PATCH 14/14] mm: Account for WRITEBACK_TEMP in balance_dirty_pages Maxim Patlasov
2012-11-16 17:10 ` Maxim Patlasov
2012-11-21 12:01 ` Maxim Patlasov
2012-11-21 12:01 ` Maxim Patlasov
2012-11-22 13:27 ` Jaegeuk Hanse [this message]
2012-11-22 13:27 ` Jaegeuk Hanse
2012-11-22 13:56 ` Maxim V. Patlasov
2012-11-22 13:56 ` Maxim V. Patlasov
2012-11-22 13:56 ` Maxim V. Patlasov
2012-11-27 1:04 ` [PATCH v2 00/14] fuse: An attempt to implement a write-back cache policy Feng Shuo
2012-11-27 7:56 ` Maxim V. Patlasov
[not found] ` <50B47243.9080706-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
2012-11-27 15:19 ` Feng Shuo
2012-12-12 14:53 ` Maxim V. Patlasov
2013-01-15 15:20 ` Maxim V. Patlasov
2013-01-25 10:21 ` Miklos Szeredi
2013-01-25 12:50 ` Maxim V. Patlasov
2013-01-25 12:50 ` Maxim V. Patlasov
-- strict thread matches above, loose matches on Subject: below --
2013-01-25 18:20 [PATCH v3 " Maxim V. Patlasov
[not found] ` <20130125181700.10037.29163.stgit-vWG5eQQidJHciZdyczg/7Q@public.gmane.org>
2013-01-25 18:28 ` [PATCH 14/14] mm: Account for WRITEBACK_TEMP in balance_dirty_pages Maxim V. Patlasov
2013-01-25 18:28 ` Maxim V. Patlasov
2013-04-01 10:40 [PATCH v4 00/14] fuse: An attempt to implement a write-back cache policy Maxim V. Patlasov
[not found] ` <20130401103749.19027.89833.stgit-vWG5eQQidJHciZdyczg/7Q@public.gmane.org>
2013-04-01 10:42 ` [PATCH 14/14] mm: Account for WRITEBACK_TEMP in balance_dirty_pages Maxim V. Patlasov
2013-04-01 10:42 ` Maxim V. Patlasov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=50AE2842.3060509@gmail.com \
--to=jaegeuk.hanse@gmail.com \
--cc=dev@parallels.com \
--cc=fuse-devel@lists.sourceforge.net \
--cc=jbottomley@parallels.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=miklos@szeredi.hu \
--cc=mpatlasov@parallels.com \
--cc=viro@zeniv.linux.org.uk \
--cc=xemul@parallels.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.